Dual-Dimensional Gaussian Splatting Integrating 2D and 3D Gaussians for Surface Reconstruction
Year: 2025
Type: article
Abstract: Three-Dimensional Gaussian Splatting (3DGS) has revolutionized novel-view synthesis, enabling real-time rendering of high-quality scenes. Two-Dimensional Gaussian Splatting (2DGS) improves geometric accuracy by replacing 3D Gaussians with flat 2D Gaussians. However, the flat nature of 2D Gaussians reduces mesh quality on volumetric surfaces and results in over-smoothed reconstruction. To address this, we propose Dual-Dimensional Gaussian Splatting (DDGS), which integrates both 2D and 3D Gaussians. First, we generalize the homogeneous transformation matrix based on 2DGS to initialize all Gaussians in 3D. Subsequently, during training, we selectively convert Gaussians into 2D representations based on their scale. This approach leverages the complementary strengths of 2D and 3D Gaussians, resulting in more accurate surface reconstruction across both flat and volumetric regions. Additionally, to mitigate over-smoothing, we introduce gradient-based regularization terms. Quantitative evaluations on the DTU and TnT datasets demonstrate that DDGS consistently outperforms prior methods, including 3DGS, SuGaR, and 2DGS, achieving the best Chamfer Distance and F1 score across a wide range of scenes.
Source: Applied Sciences
DOI: 10.3390/app15126769
Authors: Jichan Park, Jae-Won Suh, Yuseok Ban
Institution: Chungbuk National University
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,896
OpenAlex ID: W4411338391